Fact · Dictation software
The nerd-dictation README says the speech model is a local folder, by default in the user's configuration directory.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“Language Model ``~/.config/nerd-dictation/model`` ... Note that ``--vosk-model-dir=PATH`` can be used to override the default.”
nerd-dictation: Offline Speech to Text for Desktop Linux, Campbell Barton, GitHub, 2026, Paths.
Open the original- What it measures
- The Paths section of the README lists the model folder that the recognizer loads.
- What it does not show
- The README gives the model path, not a statement such as 'on-device'. The row rests on the model being a local folder.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as nerd-dictation: local VOSK model: 1 1 = yes, 0 = no.
- App
- nerd-dictation
- Feature
- Speech processed on the device
- Detail
- local VOSK model
- As of
- 2026-10
- Note
- 1 means the maker's page says the app does this